AI Paper Atlas

Research map / Point clouds / Segmentation and detection

ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation

Tsung-Han Wu, Yueh-Cheng Liu, Yu-Kai Huang, Hsin-Ying Lee, Hung-Ting Su, Ping-Chia Huang, Winston H. Hsu

ICCV 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 80 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use sub-scene regions instead of whole scans as query unit (ablation)ENT selection · S3DIS Area5mIoU: over 10 %Improved
add diversity-aware selection (cluster penalization) (ablation)ENT + Region · S3DIS Area5mIoUImproved
add color discontinuity and structural complexity to the score (ablation)ReDAL · S3DIS Area5mIoU: helpful when labeled points larger than 9 %Mixed
add color and structure to entropy without diversity module (ablation)ENT + Region · S3DIS Area5mIoUNo clear effect
use ReDAL instead of random scan selectionSPVCNN · S3DIS Area5 (15% labeled)mIoU: 49.02 -> 57.97Improved
use ReDAL instead of random scan selectionMinkowskiNet · SemanticKITTI (5% labeled)mIoU: 54.67 -> 59.76Improved
use softmax entropy scan selection instead of random selectionSPVCNN · S3DIS Area5 (15% labeled)mIoU: 49.02 -> 45.06Hurt
use Core-Set selection instead of random selectionSPVCNN · S3DIS Area5 (15% labeled)mIoU: 49.02 -> 41.40Hurt
ReDAL labeling instead of full labels on bicycle classReDAL · SemanticKITTI (5% labeled)bicycle IoU: 20.3 -> 29.5Improved
ReDAL labeling instead of full labels on average IoUReDAL · SemanticKITTI (5% labeled)average IoU: 61.4 -> 59.8Hurt
vary kNN size, decay rate eta and number of clusters (ablation)ReDAL · S3DIS / SemanticKITTImIoUNo clear effect

Later papers that compared with this method

2 later accepted papers report ReDAL as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy